© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 3839
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to court cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding arguments or assertions

    np_acts-logits-general · gemini-2.0-flash

    legal arguments made by parties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    spiller
    -0.59
     confirming
    -0.58
    aktu
    -0.56
     تشکر
    -0.56
     connaît
    -0.55
    spath
    -0.54
    <bos>
    -0.54
    '>{
    -0.53
    räck
    -0.53
    Obrigado
    -0.53
    POSITIVE LOGITS
     argue
    1.28
     argued
    1.22
     contend
    1.17
     contended
    1.14
     contends
    1.09
     maintain
    1.08
     argues
    1.06
     contention
    1.06
     maintains
    1.03
     arguing
    1.03
    Activations Density 0.667%

    No Known Activations